Agency Swarm is an open-source framework developed to facilitate the creation and management of collaborative AI agents, referred to as 'swarms.' By enabling multiple agents with distinct roles and capabilities to work together, it aims to automate complex workflows within AI development and other applications. The framework provides tools for defining agent behaviors, managing inter-agent communication, and integrating with existing systems, thereby enhancing efficiency and scalability in AI-driven projects.

Agency Swarm

agency-swarm

An open-source AI agent orchestration framework designed to automate and streamline AI development processes through collaborative agent swarms.

Agent4Rec is an innovative recommender system simulator that leverages Large Language Models (LLMs) to create 1,000 generative agents, each initialized from the MovieLens-1M dataset. These agents exhibit diverse social traits and preferences, engaging in realistic interactions with personalized movie recommendations. Actions include watching, rating, evaluating, exiting, and conducting interviews about recommended content. Designed to provide insights into human behavior within recommendation environments, Agent4Rec serves as a valuable tool for researchers and developers aiming to study and enhance recommender systems.

Agent4Rec

agent4rec

An open-source recommender system simulator utilizing 1,000 LLM-empowered generative agents to emulate user interactions with personalized movie recommendations.

smolagents is a streamlined, open-source library developed by Hugging Face that enables developers to create powerful AI agents with just a few lines of code. The library emphasizes simplicity, containing approximately a thousand lines of code, and offers first-class support for Code Agents—agents that write their actions in Python code. smolagents is compatible with a wide range of language models, including those from OpenAI, Anthropic, and models hosted on the Hugging Face Hub. To ensure secure code execution, it provides options for running code in sandboxed environments via E2B. The library also integrates with the Hugging Face Hub, allowing users to share and load tools seamlessly.

smolagents

A lightweight, open-source library by Hugging Face for building AI agents with minimal code, supporting various language models and secure code execution.

Yawning Titan is an abstract, graph-based cyber-security simulation environment designed to facilitate the training of intelligent agents for autonomous cyber operations. Developed by the Defence Science and Technology Laboratory (Dstl), it focuses on enabling defensive autonomous agents to counter probabilistic red (attacker) agents within simulated network environments. Built on OpenAI's Gym framework, Yawning Titan supports a wide range of reinforcement learning algorithms and offers flexible environment configurations, making it a valuable tool for research and development in cyber defense strategies.

Yawning Titan

yawning-titan

An open-source, graph-based cyber-security simulation environment for training intelligent agents in autonomous cyber defense operations.

AgentKit is an open-source starter kit developed by BCG X, the tech build and design unit of Boston Consulting Group. It leverages LangChain, FastAPI, and Next.js to enable developers to quickly build and experiment with agent applications. AgentKit offers a modular and easily configurable tech stack, including a React/Next.js chat-based UI designed for agents, featuring streaming, rendering of tables, visualizations, code, and status tracking of agent actions. The toolkit emphasizes reliability through an easy-to-configure routing architecture, allowing control over possible paths an agent can take, making it suitable for real-life use cases. Additionally, AgentKit is set up to scale to MVP with ready-made queue management, authentication, caching, and monitoring.

AgentKit

agentkit

A LangChain-based starter kit developed by BCG X for rapidly building high-quality agent applications with a flexible UI and reliable architecture.

Apollo AI, developed by Augmented Intelligence (AUI), is a revolutionary language model that integrates the conversational abilities of generative AI with the predictability and actionability of rule-based AI. This neuro-symbolic architecture enables businesses to deploy AI agents that are not only capable of engaging in natural language conversations but also adhere to specific operational rules and guidelines. Apollo AI is designed to be fine-tuned for various use cases, providing companies with the tools to create agents that are safe, reliable, and tailored to their unique requirements. In collaboration with Google Cloud, AUI offers Apollo AI as a scalable solution for enterprises seeking to enhance customer interactions and operational efficiency.

Apollo AI

apollo-ai

A groundbreaking language model developed by AUI, combining generative and rule-based AI to create controllable and reliable conversational agents for businesses.

Langroid is an open-source Python framework designed to streamline the development of applications powered by Large Language Models (LLMs). It introduces a multi-agent programming paradigm, treating agents as first-class citizens to manage multiple LLM conversations, each responsible for different aspects of a task. This approach facilitates efficient collaboration through message exchange, enabling developers to build complex, intelligent applications with ease. Langroid supports integration with various LLMs, vector databases, and function-calling tools, offering a modular and extensible architecture for AI application development.

Langroid

langroid

An open-source Python framework that simplifies LLM application development using a multi-agent programming paradigm.

ChatArena is an open-source Python framework designed to facilitate the development of multi-agent language game environments for large language models (LLMs). It provides a flexible structure for defining multiple players, environments, and their interactions, enabling researchers and developers to explore and enhance AI communication and collaboration skills. With user-friendly interfaces, including both web UI and command-line options, ChatArena supports the creation of diverse language game scenarios, such as conversational simulations, educational settings, and social deduction games.

ChatArena

chatarena

An open-source framework for creating multi-agent language game environments to enhance AI communication and collaboration capabilities.

FloAI is an open-source Python framework designed to streamline the development of composable AI agents and workflows. It enables developers to build, launch, and scale autonomous AI applications efficiently by providing a flexible, modular approach to constructing agent-based systems. With features like YAML-based configuration, support for various agent types, and integration with tools from the LangChain community, FloAI facilitates the creation of sophisticated AI solutions tailored to specific needs.

FloAI

floai

An open-source Python framework that simplifies the creation of composable AI agents and workflows for complex tasks.

Restack is an open-source framework designed to assist engineers in creating, deploying, and scaling autonomous AI applications. It offers a comprehensive suite of tools, including the Restack AI Framework for coding multistep workflows with features like concurrency, scheduling, retries, and rate-limiting. Additionally, the Restack Desktop provides a developer environment with a user interface to visualize and debug workflows, enhancing the development process. By leveraging Restack, developers can build resilient AI products capable of running long-lived processes with persistent state, facilitating the creation of autonomous agents that self-improve over time based on feedback loops and long-term memory.

Restack

restack

An open-source framework empowering developers to build, launch, and scale autonomous AI products efficiently.

Ax is an open-source TypeScript framework designed to facilitate the development of agents and workflows powered by large language models (LLMs). Inspired by Stanford's DSPy paper, Ax provides tools for creating chat interfaces, retrieval-augmented generation (RAG) systems, streaming applications, and multi-modal interactions. It supports various LLMs and vector databases, offers automatic prompt generation from simple signatures, and includes features like output validation during streaming, multi-agent orchestration, and OpenTelemetry tracing for observability. Ax aims to streamline the creation of efficient, production-ready AI applications.

An open-source TypeScript framework for building LLM-powered agents and agentic workflows.

LiteLLM is an open-source toolkit that streamlines interactions with over 100 large language models (LLMs) by providing a unified API in the OpenAI format. It offers both a Python SDK and a proxy server (LLM Gateway) to manage authentication, load balancing, and spend tracking across various LLM providers, including OpenAI, Azure OpenAI, Vertex AI, and Amazon Bedrock. LiteLLM supports features such as retry and fallback logic, rate limiting, and logging integrations with tools like Langfuse and OpenTelemetry. It is designed to simplify the integration of multiple LLMs into applications, ensuring consistent output formats and efficient resource management.

LiteLLM

litellm

An open-source Python SDK and proxy server for managing authentication, load balancing, and spend tracking across 100+ LLMs using a unified OpenAI format.

Browse Agentic AI Category: "AI Agent Development Frameworks"